Simulation engagement points for long running threads

1. A computer-implemented method for determining simulation engagement points for chat threads, the computer-implemented method comprising the steps of: monitoring, by one or more computer processors, one or more chat threads to create a prior chat discourse, wherein the prior chat discourse contains one or more chat data, an author posting frequency of the participants in the chat thread of the one or more chat threads, and an author role of the participants in the chat thread of the one or more chat threads; determining, by one or more computer processors, whether a new author has entered any chat thread of the one or more chat threads based on the prior chat discourse; responsive to determining that the new author has entered any chat thread of the one or more chat threads, analyzing, by one or more computer processors, the prior chat discourse using topic modeling techniques to create a corpus of linguistic analysis, wherein the corpus of linguistic analysis includes one or more terms of the chat thread of the one or more chat threads and a log-likelihood of the terms of the chat thread of the one or more chat threads; creating, by one or more computer processors, a social graph of participants in the chat thread of the one or more chat threads based on the prior chat discourse; analyzing, by one or more computer processors, the social graph of the participants in the chat thread of the one or more chat threads using cosine similarity to create an author analysis database, wherein the author analysis database contains a similarity scores between the participants in the chat thread of the one or more chat threads; analyzing, by one or more computer processors, the author posting frequency of the participants in the chat thread of the one or more chat threads to create a collection class of the author posting frequency of the participants in the chat thread, wherein the collection class of the author posting frequency contains a derived results of the posting frequency of the participants in the chat thread of the one or more chat threads; combining, by one or more computer processors, the corpus of linguistic analysis and the author analysis database to create a discourse injection point model of participants in the chat thread of the one or more chat threads; establishing, by one or more computer processors, an optimal in time injection point, wherein the optimal in time injection point is determined from a confluence of the corpus of linguistic analysis, the author analysis database, and the collection class of the author posting frequency; and injecting, by one or more computer processors, the new author into the any chat thread of the one or more chat threads at the optimal in time injection point.

2. The computer-implemented method of claim 1 , wherein injecting the new author into the any chat thread of the one or more chat threads at the optimal in time injection point further comprises using, by one or more computer processors, the discourse injection point model to provide a visual overlay.

3. The computer-implemented method of claim 2 , wherein providing the visual overlay further comprises displaying, by one or more computer processors, the visual overlay as a thermograph visual representation.

4. The computer-implemented method of claim 1 , wherein the topic modeling techniques to create the corpus of linguistic analysis further comprises using, by one or more computer processors, a Latent Dirichlet Allocation model to analyze an interaction and visibility of the participants in the chat thread of the one or more chat threads by topic.

5. The computer-implemented method of claim 1 , wherein the topic modeling techniques to create the corpus of linguistic analysis further comprises using, by one or more computer processors, a BiTerm Model to analyze an interaction and visibility of the participants by topic.

6. The computer-implemented method of claim 1 , further comprising: determining, by one or more computer processors, whether any chat thread of the one or more chat threads has ended; and responsive to determining that the any chat thread of the one or more chat threads has ended, providing, by one or more computer processors, a thread summary report for the any chat thread of the one or more chat threads has ended.

7. The computer-implemented method of claim 1 , wherein determining whether the new author has entered any chat thread of the one or more chat threads further comprises determining, by one or more computer processors, that the new author previously participated in a current thread, and a length of time since the new author last posted exceeds a default threshold.

8. A computer-implemented method for embodying an expert system into a chat bot, the computer-implemented method comprising the steps of: monitoring, by one or more computer processors, one or more chat threads to create a prior chat discourse, wherein the prior chat discourse contains one or more chat data, an author posting frequency of the participants in the chat thread of the one or more chat threads, and an author role of the participants in the chat thread of the one or more chat threads; analyzing, by one or more computer processors, the prior chat discourse using topic modeling techniques to create a corpus of linguistic analysis, wherein the corpus of linguistic analysis includes one or more terms of a chat thread of the one or more chat threads and a log-likelihood of the terms of the chat thread of the one or more chat threads; creating, by one or more computer processors, a social graph of participants in the one or more chat threads based on the prior chat discourse; analyzing, by one or more computer processors, the social graph of the participants in the one or more chat threads to create an author analysis database; determining, by one or more computer processors, whether a new message was posted to a chat thread of the one or more chat threads; determining, by one or more computer processors, whether the new message posted to the chat thread of the one or more chat threads is related to prior posts by a particular participant in the chat thread of the one or more chat threads based on the corpus of linguistic analysis and the author analysis database; responsive to determining that the new message posted to the chat thread of the one or more chat threads is related to prior posts by a particular participant in the chat thread of the one or more chat threads, determining, by one or more computer processors, whether the particular participant in the chat thread of the one or more chat threads is still available in the chat thread of the one or more chat threads based on the prior chat discourse; responsive to determining that the particular participant in the chat thread of the one or more chat threads is not still available in the chat thread of the one or more chat threads, modifying, by one or more computer processors, the chat thread of the one or more chat threads to create a modified chat thread, wherein the modified chat thread includes scaffolding chat, wherein the scaffolding chat uses an expert system based on the corpus of linguistic analysis and the author analysis database; and embodying, by one or more computer processors, the expert system of the particular participant in the chat thread of the one or more chat threads into a chat bot to propagate scaffolding chat in the chat thread of the one or more chat threads.

9. The computer-implemented method of claim 8 , wherein the topic modeling techniques to create the corpus of linguistic analysis further comprises using, by one or more computer processors, a Latent Dirichlet Allocation model to analyze an interaction and visibility of the participants by topic.

10. The computer-implemented method of claim 8 , wherein the topic modeling techniques to create the corpus of linguistic analysis further comprises using, by one or more computer processors, a BiTerm Model to analyze an interaction and visibility of the participants by topic.

11. The computer-implemented method of claim 8 , wherein analyzing the social graph of the participants in the one or more chat threads to create the author analysis database further comprises using, by one or more computer processors, cosine similarity to calculate a similarity score of the participants in the chat thread of the one or more chat threads.

12. The computer-implemented method of claim 8 , wherein determining whether the particular participant in the chat thread is still available in the chat thread of the one or more chat threads further comprises: waiting, by one or more computer processors, a pre-determined length of time after the new message is posted to the chat thread; and responsive to determining that the particular participant in the chat thread has not responded to the new message posted to the chat thread, determining, by one or more computer processors, that the particular participant in the chat thread is not available.

13. The computer-implemented method of claim 8 , further comprising: determining, by one or more computer processors, whether the particular participant in the chat thread has returned to the chat thread; and responsive to determining that the particular participant in the chat thread has returned to the chat thread, providing, by one or more computer processors, a bot summary report for the chat thread.

14. A computer system for determining simulation engagement points for chat threads, the computer system comprising: one or more computer processors; one or more computer readable storage media; and program instructions stored on the one or more computer readable storage media for execution by at least one of the one or more computer processors, the stored program instructions comprising: program instructions to monitor one or more chat threads to create a prior chat discourse, wherein the prior chat discourse contains one or more chat data, an author posting frequency of the participants in the chat thread of the one or more chat threads, and an author role of the participants in the chat thread of the one or more chat threads; program instructions to determine whether a new author has entered any chat thread of the one or more chat threads based on the prior chat discourse; responsive to determining that the new author has entered any chat thread of the one or more chat threads, program instructions to analyze the prior chat discourse using topic modeling techniques to create a corpus of linguistic analysis, wherein the corpus of linguistic analysis includes one or more terms of the chat thread of the one or more chat threads and a log-likelihood of the terms of the chat thread of the one or more chat threads; program instructions to create a social graph of participants in the chat thread of the one or more chat threads based on the prior chat discourse; program instructions to analyze the social graph of the participants in the chat thread of the one or more chat threads using cosine similarity to create an author analysis database, wherein the author analysis database contains a similarity scores between the participants in the chat thread of the one or more chat threads; program instructions to analyze the author posting frequency of the participants in the chat thread of the one or more chat threads to create a collection class of the author posting frequency, wherein the collection class of the author posting frequency contains a derived results of the posting frequency of the participants in the chat thread of the one or more chat threads; program instructions to combine the corpus of linguistic analysis and the author analysis database to create a discourse injection point model of participants in the chat thread of the one or more chat threads; program instructions to establish an optimal in time injection point, wherein the optimal in time injection point is determined from a confluence of the corpus of linguistic analysis, the author analysis database, and the collection class of the author posting frequency; and program instructions to inject the new author into the any chat thread of the one or more chat threads at the optimal in time injection point.

15. The computer system of claim 14 , wherein injecting the new author into the any chat thread of the one or more chat threads at the optimal in time injection point further comprises program instructions to use the discourse injection point model to provide a visual overlay.

16. The computer system of claim 15 , wherein providing the visual overlay further comprises program instructions to display the visual overlay as a thermograph visual representation.

17. The computer system of claim 14 , wherein the topic modeling techniques to create the corpus of linguistic analysis further comprises program instructions to use a Latent Dirichlet Allocation model to analyze an interaction and visibility of the participants in the chat thread of the one or more chat threads by topic.

18. The computer system of claim 14 , wherein the topic modeling techniques to create the corpus of linguistic analysis further comprises program instructions to use a BiTerm Model to analyze an interaction and visibility of the participants by topic.

19. The computer system of claim 14 , further comprising: program instructions to determine whether any chat thread of the one or more chat threads has ended; and responsive to determining that the any chat thread of the one or more chat threads has ended, program instructions to provide a thread summary report for the any chat thread of the one or more chat threads that has ended.

20. The computer system of claim 14 , wherein determining whether the new author has entered any chat thread of the one or more chat threads further comprises program instructions to determine that the new author previously participated in a current thread, and a length of time since the new author last posted exceeds a default threshold.